Skip to main content
Glama

load_state

Read-only

Reads a mind map or flowchart by docId and reports whether it changed since a specified revision, helping clients decide when to refresh the diagram.

Instructions

The view reads the diagram, or learns it is up to date.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "docId": "<docId>"
    },
    "name": "load_state"
  }
}

Input Schema

NameRequiredDescriptionDefault
docIdYesThe docId a visualize result gave you
sinceRevisionNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.6/5.0
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already establish readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description does add real behavioral signal beyond that: the call may return the diagram or report that nothing changed, implying a short-circuit/not-modified outcome. It still omits what that outcome looks like and any size or error behavior, so 3 rather than higher.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

One short, front-loaded sentence with no filler, which is structurally good. However, the brevity is achieved through cryptic phrasing ('The view reads the diagram') that costs clarity rather than saving the reader anything.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 2-parameter read with no output schema, the description needs to explain the return contract and the revision-check semantics, and it only gestures at both. The conditional behavior is present but the meaning of 'up to date' (no payload returned? empty result?) is left for the agent to guess.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50% – docId is documented ('The docId a visualize result gave you') while sinceRevision has no schema description at all. The description's 'learns it is up to date' indirectly explains that sinceRevision is a change-detection cursor, which is genuine added meaning, but it gives no format, monotonicity, or behavior when the revision is stale or ahead.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

The sentence is metaphorical and refers to 'the view' and 'the diagram' without ever saying what load_state actually returns or how it relates to a document. An agent cannot tell whether it retrieves diagram content, a revision token, or both, and nothing distinguishes it from siblings like get_diagram or visualize.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no statement of when to call this instead of get_diagram or after save_state, and no prerequisites such as needing a docId from a prior visualize call (that is only in the schema). The 'or learns it is up to date' clause hints at a conditional call pattern but never names the condition or the alternative tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.